[PATCH 05/10] mm: page_alloc: make find_next_best_node could skip DRAM node

From: Yang Shi
Date: Sat Mar 23 2019 - 00:46:27 EST


Need find the cloest non-DRAM node to demote DRAM pages. Add
"skip_ram_node" parameter to find_next_best_node() to skip DRAM node on
demand.

Signed-off-by: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
---
mm/internal.h | 11 +++++++++++
mm/page_alloc.c | 15 +++++++++++----
2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 9eeaf2b..46ad0d8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -292,6 +292,17 @@ static inline bool is_data_mapping(vm_flags_t flags)
return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
}

+#ifdef CONFIG_NUMA
+extern int find_next_best_node(int node, nodemask_t *used_node_mask,
+ bool skip_ram_node);
+#else
+static inline int find_next_best_node(int node, nodemask_t *used_node_mask,
+ bool skip_ram_node)
+{
+ return 0;
+}
+#endif
+
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 68ad8c6..07d767b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5375,6 +5375,7 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
* find_next_best_node - find the next node that should appear in a given node's fallback list
* @node: node whose fallback list we're appending
* @used_node_mask: nodemask_t of already used nodes
+ * @skip_ram_node: find next best non-DRAM node
*
* We use a number of factors to determine which is the next node that should
* appear on a given node's fallback list. The node should not have appeared
@@ -5386,7 +5387,8 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
*
* Return: node id of the found node or %NUMA_NO_NODE if no node is found.
*/
-static int find_next_best_node(int node, nodemask_t *used_node_mask)
+int find_next_best_node(int node, nodemask_t *used_node_mask,
+ bool skip_ram_node)
{
int n, val;
int min_val = INT_MAX;
@@ -5394,13 +5396,19 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
const struct cpumask *tmp = cpumask_of_node(0);

/* Use the local node if we haven't already */
- if (!node_isset(node, *used_node_mask)) {
+ if (!node_isset(node, *used_node_mask) &&
+ !skip_ram_node) {
node_set(node, *used_node_mask);
return node;
}

for_each_node_state(n, N_MEMORY) {

+ /* Find next best non-DRAM node */
+ if (skip_ram_node &&
+ (node_isset(n, def_alloc_nodemask)))
+ continue;
+
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
continue;
@@ -5432,7 +5440,6 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
return best_node;
}

-
/*
* Build zonelists ordered by node and zones within node.
* This results in maximum locality--normal zone overflows into local
@@ -5494,7 +5501,7 @@ static void build_zonelists(pg_data_t *pgdat)
nodes_clear(used_mask);

memset(node_order, 0, sizeof(node_order));
- while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+ while ((node = find_next_best_node(local_node, &used_mask, false)) >= 0) {
/*
* We don't want to pressure a particular node.
* So adding penalty to the first node in same
--
1.8.3.1